ICM-Assistant: Instruction-tuning Multimodal Large Language Models for Rule-based Explainable Image Content Moderation
Controversial contents largely inundate the Internet, infringing various cultural norms and child protection standards. Traditional Image Content Moderation (ICM) models fall short in producing precise moderation decisions for diverse standards, while recent multimodal large language models (MLLMs), when adopted to general rule-based ICM, often produce classification and explanation results that are inconsistent with human moderators. Aiming at flexible, explainable, and accurate ICM, we design a novel rule-based dataset generation pipeline, decomposing concise human-defined rules and leveraging well-designed multi-stage prompts to enrich short explicit image annotations. Our ICM-Instruct dataset includes detailed moderation explanation and moderation Q-A pairs. Built upon it, we create our ICM-Assistant model in the framework of rule-based ICM, making it readily applicable in real practice. Our ICM-Assistant model demonstrates exceptional performance and flexibility. Specifically, it significantly outperforms existing approaches on various sources, improving both the moderation classification (36.8% on average) and moderation explanation quality (26.6% on average) consistently over existing MLLMs. Code/Data is available at https://github.com/zhaoyuzhi/ICM-Assistant.
Code (1)
Tasks
Dataset GenerationSimilar Papers 제목 키워드 기반
Visual Instruction Tuning
Instruction tuning large language models (LLMs) using machine-generated instruction-following data has improved zero-shot capabilities on new tasks, but the idea is less explored in the multimodal field. In this paper, w…
1 Image, 2*2 Stitching3D Question Answering (3D-QA)Image ClassificationImage Retrieval+9Generative Visual Instruction Tuning
We propose to use automatically generated instruction-following data to improve the zero-shot capabilities of a large multimodal model with additional support for generative and image editing tasks. We achieve this by cu…
Image GenerationImage-text matchingInstruction FollowingLanguage Modeling+4Multi-Modal Instruction-Tuning Small-Scale Language-and-Vision Assistant for Semiconductor Electron Micrograph Analysis
We present a novel framework for analyzing and interpreting electron microscopy images in semiconductor manufacturing using vision-language instruction tuning. The framework employs a unique teacher-student approach, lev…
Instruction FollowingQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning
With the rapid development of large language models (LLMs) and their integration into large multimodal models (LMMs), there has been impressive progress in zero-shot completion of user-oriented vision-language tasks. How…
Chart UnderstandingValley: Video Assistant with Large Language model Enhanced abilitY
Large language models (LLMs), with their remarkable conversational capabilities, have demonstrated impressive performance across various applications and have emerged as formidable AI assistants. In view of this, it rais…
Action RecognitionInstruction FollowingLanguage ModelingLanguage Modelling+3